ContractSense AI is a production-ready Retrieval-Augmented Generation (RAG) web application that analyzeslegal contracts for risk, surfaces dangerous clauses, and enables interactive question-answering over uploadedPDF documents. The system combines FastAPI with LangChain orchestration, a locally running sentencetransformer embedding model (all-MiniLM-L6-v2), and the Groq-hosted Llama 3.3 70B large language modelfor fast inference. A custom NumpyVectorStore provides lightweight vector similarity search without externaldatabase dependencies. The frontend features an animated Three.js landing page and a fully interactive threepanel dashboard with risk gauge, red-flag cards, TL;DR summary, and RAG-powered conversational chat. Allembedding computation runs locally — no cloud embedding API is required — making the system inherentlyprivacy-preserving and cost-free to operate at the inference layer. The system is designed for deployment onstandard personal computing hardware without requiring GPU acceleration, making it accessible to students,freelancers, and small organisations with limited IT infrastructure